Skip to content

Home / Monte Carlo / Model Building / Create Empirical

Create Empirical

From Excel click...

QXL Monte Carlo New > Design > Create/Modify Design Sheet > Create Empirical

Adds a worksheet for one Empirical distribution: a column of your own sample data, used directly as the distribution rather than through a fitted shape.

There is no dialog. Create Empirical asks for a name, adds the sheet, and tells you where to type.

How it works

  1. Press Create Empirical. It asks for a name:

    Name for the new empirical distribution:

  2. Type a name and press OK. The name is checked, and an unusable one is refused and asked for again. Cancelling stops without adding anything.

  3. A new worksheet is added at the end of the workbook, named Empirical (your name). Excel caps a sheet name at 31 characters, so a long name is shortened to fit, and a number is added if that sheet name is already taken.
  4. The name is written into B2 as a bold, centred, pale blue, bordered title cell.

  5. A message says what to do next:

    A new sheet was added for the empirical distribution 'Cycle time'. Enter the sample data in the column directly below the title 'Cycle time' (cell B3 and down).

  6. The sheet opens with B3 already selected. Type or paste your data down column B.

What makes it an Empirical distribution

The title cell carries a hidden marker that Quantum XL looks for when it scans the workbook. That marker on B2, and the data in the column below it, are the whole definition. Nothing else on the sheet matters, and the sheet can be renamed.

Do not delete or move the title cell. Without it the sheet is an ordinary sheet of numbers and the distribution disappears from the list.

The data

The data is every numeric cell in the title cell's column, from the row below the title down to the last used row of the sheet.

  • Order does not matter. The values are used as a set, and Quantum XL sorts them itself.
  • Blank cells and text are skipped, not refused, so a note or a heading under the data does not break the distribution.
  • A blank row does not end the data. Reading continues to the last used row of the sheet, so a gap in the column is skipped rather than treated as the end.

Names that are refused

The name What it says
blank Enter a name for the empirical distribution.
already used by another Empirical variable An empirical distribution named 'Cycle time' already exists in this workbook. Choose a different name.
a built-in or custom distribution name 'Normal' is already a distribution name; a distribution's data would be found first. Choose a different name.

The second rule exists because a name that clashes with a built-in or custom distribution could never be reached: the model resolves those first, so the Empirical data would never be sampled.

Names are compared ignoring capitalisation and surrounding spaces.

Using it

An Empirical variable appears at the end of the distribution list wherever that list is shown, as its name followed by (Empirical).

Two kinds of distribution are defined in the workbook rather than chosen from the list, and both are added to the end of it.

A custom distribution is one you build yourself. It appears under the name you gave it.

An Empirical variable is a column of your own sample data. It appears as its name followed by (Empirical).

Neither has parameter boxes, because neither keeps its data in the marking: the data stays in the workbook and the model reads it from there. Selecting one and marking writes only its name.

Two sheets with the same name

When two sheets define the same distribution name, the first one found keeps it and the other is ignored.

Workbooks from Quantum XL v17

An Empirical sheet made by v17 is read unchanged. v17 wrote the marker under a misspelled name, and Quantum XL still looks for both spellings, so existing workbooks keep working. A sheet that somehow carries both is read through the current one.

  • Custom Distributions, for a shape you define rather than data you collected. Its Fit from data button builds one from a raw data column, which is the other way to turn measurements into a distribution.
  • Supported Distributions, the built-in shapes.
  • Mark Input, where you choose the distribution for a cell.